"Understanding Server-Sent Events (SSE)" matching MCP tools:

• tower_replay

  fomox402 — Last-Bidder-Wins on Solana

  Replay ordered tower events for a single (firm, game) pair. WHAT IT DOES: GETs /v1/replay/firm/:firm/game/:game. Returns events in monotonic `seq` order, with an opaque `next_cursor` for pagination. Read only, no auth required. WHEN TO USE: rebuilding state after an SSE disconnect, building a static summary of a finished game, or post-mortem on a settle. Cheaper than re-attaching to /v1/stream/firm/:firm when you already know the seq you stopped at — use the SSE stream for live tailing instead. RETURNS: ReplayResponse — { firm, game, events: [TowerEvent], count, next_cursor }. Each TowerEvent has { seq, ts (unix ms), type, firm, game, agent_wallet, data }. PAGINATION: pass the previous response's `next_cursor` as `cursor`. When `next_cursor` is null you've reached head of stream. RELATED: tower_floors (current snapshot), firm_ingest (publish events).

  Connector

• tflogs

  InsideOut (Riley)

  MONITORING: Fetch Terraform deployment logs with pagination Fetches logs from a running or completed Terraform deployment job. For **completed jobs**: uses REST endpoint for instant retrieval (supports `tail` for server-side filtering). For **running jobs**: streams via SSE with timeout-based pagination. **PAGINATION** (running jobs only): Use `last_event_id` from the response to fetch more: 1. First call: `tflogs(session_id='...')` → get logs + `last_event_id` 2. Next call: `tflogs(session_id='...', last_event_id='...')` → get NEW logs only 3. Repeat until `complete: true` in response **RESPONSE FIELDS**: - `logs`: Array of log messages collected - `last_event_id`: Pass this back to get more logs (pagination cursor, SSE only) - `complete`: true if job finished, false if more logs may be available - `total_logs`: total log entries before tail truncation REQUIRES: session_id from convoopen response (format: sess_v2_...). OPTIONAL: job_id to target a specific deployment (use tfruns to discover IDs), timeout (default 50s, max 55s), last_event_id (for pagination), tail (return only last N entries) ⚠️ CONTEXT WARNING: Deploy logs can be hundreds of lines. Use tail: 50 for completed jobs to avoid blowing up the context window.

  Connector

• get_me

  Backtest360

  The configured API key's permissions, limits, and current usage. Cheap. Call early in a session — before planning work — to learn what this key can do instead of discovering limits through failed calls. Returns: ``scopes``: the permission scopes the key carries. ``limits``: requests per minute and per day, max concurrent requests, and the per-run bar cap (null when uncapped). ``usage``: current consumption against those limits, with reset countdowns in seconds. ``capabilities``: feature flags such as server-side data fetch and the full metric set. A small fixed-shape record, returned as the engine sent it.

  Connector

• enable_auto_deposit

  MERX - TRON Resource Exchange

  Configure automatic top-up when balance drops below a threshold. The configuration lives ONLY in the current MCP session — it is held in memory by the MCP server process and is lost on server restart, MCP client reconnect, or server redeploy. Top-ups are signed locally with TRON_PRIVATE_KEY and sent to your Merx deposit address (memo-routed). For persistent auto-deposit you currently need to call this tool again at the start of each session.

  Connector

• tower_replay

  fomox402

  Replay ordered tower events for a single (firm, game) pair. WHAT IT DOES: GETs /v1/replay/firm/:firm/game/:game. Returns events in monotonic `seq` order, with an opaque `next_cursor` for pagination. Read only, no auth required. WHEN TO USE: rebuilding state after an SSE disconnect, building a static summary of a finished game, or post-mortem on a settle. Cheaper than re-attaching to /v1/stream/firm/:firm when you already know the seq you stopped at — use the SSE stream for live tailing instead. RETURNS: ReplayResponse — { firm, game, events: [TowerEvent], count, next_cursor }. Each TowerEvent has { seq, ts (unix ms), type, firm, game, agent_wallet, data }. PAGINATION: pass the previous response's `next_cursor` as `cursor`. When `next_cursor` is null you've reached head of stream. RELATED: tower_floors (current snapshot), firm_ingest (publish events).

  Connector

• stream_task

  TunnelMind Data API

  Opens a persistent SSE connection that emits events as the task progresses. The stream closes automatically when the task reaches a terminal state or after ~90 seconds (timeout). Heartbeat comments are sent every ~15 seconds to keep the connection alive through proxies. Event types: - `status` — emitted when status changes (pending → running → complete/failed) - `result` — emitted on `complete` with the full result payload - `error` — emitted on `failed`, `cancelled`, or `expired` with error info - SSE comment (`: heartbeat`) — keepalive, no data Use this tool when: - You want real-time progress without polling. - You are in an environment that supports SSE (EventSource API). Do NOT use this tool when: - You want a simple one-shot status check — use `get_task` instead. - Your HTTP client doesn't support streaming responses. Inputs: - `task_id` (path, required): 26-char ULID. Returns: - SSE stream (`text/event-stream`). Each event is `event: <type>\\ndata: <json>\\n\\n`. Cost: - Free. Counts as one request against rate limits when the stream opens. Latency: - First event: <200ms. Stream duration: up to 90s.

  Connector

• get_recent_signals

  PredMCP

  Server-detected events from the last hour: funding outliers (≥3x 7d baseline), whale trades (≥$100k), OI caps reached. Cursor-based — pass next_cursor back as since_id to receive only new events. The polling equivalent of the /sse/signals stream. Pro tool get_signal_history covers 7 days with forward-return outcomes.

  Connector

• analyze_record

  Senzing

  Get the Senzing JSON analyzer script to validate mapped data files client-side. REQUIRED: `workspace_dir` (writable directory, e.g. ~/sz-workspace) — the call WILL FAIL without it. The analyzer validates records against the Entity Specification, examines feature distribution, attribute coverage, and data quality. Returns a Python script (no dependencies) with instructions. No source data is sent to the server. Typical workspace_dir values: Linux `/tmp` or `~/sz-workspace`; macOS `~/sz-workspace`; sandboxed envs: explicit path under home (do NOT assume /tmp exists).

  Connector

• get_action_status

  Whatcanido — MCP Server for Service Businesses

  Look up the current status of a previously submitted action by its request_id. Returns status (raw, e.g. 'new', 'sent', 'confirmed') + status_label (human, e.g. 'Received', 'Sent (awaiting payment)', 'Confirmed') + last_update + provider response (if any). Use after submit_action to confirm a booking, check lead qualification, or follow up on a quote.

  Connector

• vector_quantize

  IA-QA — 130+ QA & Dev Tools for AI Agents

  Simulate int8 or int4 quantization of float32 embedding vectors. Reduces storage by 4x (int8) or 8x (int4). Returns quantized values, scale factor, and precision loss (MSE). Useful for understanding vector DB compression trade-offs.

  Connector

• delete_invoice

  FavCRM

  Delete a DRAFT invoice. Only invoices that have never been sent can be deleted; otherwise use void_invoice.

  Connector

• stream_briefing_render_events

  storyflo

  Subscribe to real-time briefing-render events. Returns the SSE endpoint URL with the chosen filters as query params — the agent's MCP client should open it with EventSource (browser), httpx.stream / aiohttp (Python), or `curl -N` (CLI). Event types: `briefing.rendered` (daily-brief lands), `declassified.published` (new Declassified episode), `persona_briefing.rendered` (persona brief synthesised / audio rendered). Frame shape: {event_type, seq, slug, vertical, persona_slug, audio_url, published_at, metadata}. The endpoint replays the last ~1000 events on connect; a heartbeat is emitted every 30s. Public-anon read.

  Connector

• nucleus_relay

  nucleus

  Relay-substrate facade — post / read / ack / status. Actions: post - Send a relay envelope. params: {to, subject, body, sender?, priority?, in_reply_to?, context?, id?, from_session_id?} sender? auto-fills from your session role when omitted. to accepts short role aliases: main, peer, tb, ops, agy, board. "recipient" is accepted as an alias for "to". Returns {sent: bool, id: str (server message_id), error?: str}. inbox - List inbox messages. params: {role?, unread_only?, limit?} role auto-fills from CC_SESSION_ROLE env. Returns {messages: [...], role: str}. ack - Mark messages seen. params: {message_ids: [str], role?} Returns {acked: int, failed: int}. status - Diagnostic (no server call). params: {role?} Returns {is_http_mode, relay_url_set, bearer_set, canonical_role, resolved_inbox_dir}. Bearer resolves per-role at call-time (~/.tb/relay_token_<role>, falling back to NUCLEUS_RELAY_BEARER env) — never passed via this tool's prompt surface. Per ADR-0036 amendment c068abc1 + v0.2.1 Layer A.

  Connector

• test_rule

  Valuein — SEC EDGAR Fundamentals & Smart-Money Data

  Dry-run a rule's condition_expr against a SYNTHETIC trigger payload — reports whether it WOULD have fired, but NEVER dispatches the action (no report generated, no team run, no message sent, no inbox write). Use this immediately after create_rule to sanity-check the condition before it starts evaluating against real events. Pass `sample_payload_override` to test against specific field values (e.g. `{price_change_pct: 12}`).

  Connector

• subscribe_threats

  Nullcone Threat Intelligence

  Open a named, stateful subscription to live threat push delivery. Returns a subscription_id. Pass it to drain_subscription() to collect the IOCs that have arrived since your last drain — zero polling, each caller gets their own isolated stream. Multiple subscribers receive independent copies of every matching IOC. Subscriptions expire after 1 hour of inactivity (no drain calls). Composition filters let you narrow the stream: - ioc_types: only deliver these IOC types (empty = all) - families: only deliver IOCs from these malware families (empty = all) - tags: only deliver IOCs with at least one of these tags (empty = all) Requires the MCP server to be running in SSE mode (MCP_TRANSPORT=sse) with a live SpacetimeDB push subscription active. Args: min_severity: Minimum severity to deliver (0-10). Default 5 (medium+). ioc_types: List of IOC types to include. E.g. ["skill","prompt","ip"]. Valid: hash_md5, hash_sha1, hash_sha256, ip, ip_port, domain, url, yara, email, mutex, filepath, asn, ja3, imphash, cve, prompt, skill. Empty = all types. families: List of malware family names to include. Empty = all. tags: List of tags — IOC must match at least one. Empty = all. Returns: subscription_id: Opaque ID — pass to drain_subscription() / unsubscribe() push_active: Whether the background push subscription is running filters: Echo of the composition filters applied

  Connector

• excalibur_list_posts

  excalibur-mcp

  List your stored posts, server-side sorted, filtered, and offset-paginated. Optional ``status`` filter — a single status or a comma-separated set (e.g. ``draft,scheduled``), matched as set membership. ``sort_col`` is one of ``created|updated|status|scheduled`` (default ``created``); ``sort_dir`` is ``asc|desc``. ``search`` is a case-insensitive regular expression matched against the post text. ``date_from``/``date_to`` (``YYYY-MM-DD``, end-inclusive) bound the ``date_field`` column, one of ``created|updated|scheduled|sent`` (default ``created``). ``template_id`` filters to the sent occurrences a recurring template fired. ``page`` is 0-indexed; ``page_size`` is 1..100. Each row carries ``is_recurring``, ``has_dynamic``, and ``template_id`` (set on sent occurrences). Returns ``{posts:[…], total, page, page_size}`` reflecting the filtered set.

  Connector

• get_ledger

  Open Standing

  Read the append-only, hash-chained ledger of all commons events. Every entry carries a chain hash and a server-signed receipt. Use for auditing or independent verification.

  Connector

• firm_ingest

  fomox402 — Last-Bidder-Wins on Solana

  Publish a single event from a partner firm into the tower stream. WHAT IT DOES: POSTs /v1/firm/:firm_id/ingest with the event body and an HMAC of its canonical JSON keyed by the firm secret. Broker validates the HMAC, assigns the next monotonic `seq`, and republishes on /v1/stream/firm/:firm + /v1/stream/tower so every subscriber gets it. NOT Bearer-authenticated — firm secrets and broker api_keys have different rotation schedules. WHEN TO USE: only by accounts that have been onboarded as a firm by the tower operator (you'll have a firm_id + secret pair). Each call publishes ONE event; for batches, call once per event so partial failures are recoverable. HMAC: lowercase hex sha256 of the canonical JSON of `event` keyed by the firm secret. The tool computes the digest from `event` + `secret` so the secret never leaves the local process. The secret itself is NOT sent to the broker — only the digest. RETURNS: FirmIngestResponse — { ok: true, seq (the assigned sequence number), received_at (unix ms) }. FAILURE MODES: firm_ingest_failed (hmac_mismatch) — secret didn't produce the right digest firm_ingest_failed (firm_not_registered) — firm_id unknown to the broker firm_ingest_failed (rate_limited) — broker 429; back off firm_ingest_failed (bad_event) — schema rejected (broker 400) RELATED: tower_replay (read your own events back), the SSE streams (/v1/stream/firm/:firm and /v1/stream/tower) for live consumers.

  Connector

• firm_ingest

  fomox402

  Publish a single event from a partner firm into the tower stream. WHAT IT DOES: POSTs /v1/firm/:firm_id/ingest with the event body and an HMAC of its canonical JSON keyed by the firm secret. Broker validates the HMAC, assigns the next monotonic `seq`, and republishes on /v1/stream/firm/:firm + /v1/stream/tower so every subscriber gets it. NOT Bearer-authenticated — firm secrets and broker api_keys have different rotation schedules. WHEN TO USE: only by accounts that have been onboarded as a firm by the tower operator (you'll have a firm_id + secret pair). Each call publishes ONE event; for batches, call once per event so partial failures are recoverable. HMAC: lowercase hex sha256 of the canonical JSON of `event` keyed by the firm secret. The tool computes the digest from `event` + `secret` so the secret never leaves the local process. The secret itself is NOT sent to the broker — only the digest. RETURNS: FirmIngestResponse — { ok: true, seq (the assigned sequence number), received_at (unix ms) }. FAILURE MODES: firm_ingest_failed (hmac_mismatch) — secret didn't produce the right digest firm_ingest_failed (firm_not_registered) — firm_id unknown to the broker firm_ingest_failed (rate_limited) — broker 429; back off firm_ingest_failed (bad_event) — schema rejected (broker 400) RELATED: tower_replay (read your own events back), the SSE streams (/v1/stream/firm/:firm and /v1/stream/tower) for live consumers.

  Connector

• tflogs

  InsideOut (Riley)

  MONITORING: Fetch Terraform deployment logs with pagination Fetches logs from a running or completed Terraform deployment job. For **completed jobs**: uses REST endpoint for instant retrieval (supports `tail` for server-side filtering). For **running jobs**: streams via SSE with timeout-based pagination. **PAGINATION** (running jobs only): Use `last_event_id` from the response to fetch more: 1. First call: `tflogs(session_id='...')` → get logs + `last_event_id` 2. Next call: `tflogs(session_id='...', last_event_id='...')` → get NEW logs only 3. Repeat until `complete: true` in response **RESPONSE FIELDS**: - `logs`: Array of log messages collected - `last_event_id`: Pass this back to get more logs (pagination cursor, SSE only) - `complete`: true if job finished, false if more logs may be available - `total_logs`: total log entries before tail truncation REQUIRES: session_id from convoopen response (format: sess_v2_...). OPTIONAL: job_id to target a specific deployment (use tfruns to discover IDs), timeout (default 50s, max 55s), last_event_id (for pagination), tail (return only last N entries) ⚠️ CONTEXT WARNING: Deploy logs can be hundreds of lines. Use tail: 50 for completed jobs to avoid blowing up the context window.

  Connector